RESEARCH OF THE CURRENT STATE OF MACHINE LEARNING METHODS APPLICATION IN THE OIL AND GAS INDUSTRY
The extraction, refining and delivery of oil and gas products is expensive. Therefore, the main tasks of the oil and gas industry that need to be addressed are to increase the productivity of oil and gas production and minimize the cost of processing and delivery of the products to end consumers. When solving these tasks, many problems arise, such as the problems of oil and gas exploration and production, detection of anomalies in the operation of drilling rigs, detection of infrastructure risks in oil pipelines, prediction of well characteristics, minimization of expenses on oil and gas production and transportation, and detection of leaks during oil transportation and gas pipelines, risk assessment and management, forecasting oil price volatility, etc. The solution to most problems by traditional methods of data analysis is not possible, since the processes of the oil and gas industry are non-deterministic due to their non-linear nature, and also these processes generate very large amounts of data. Therefore, in the last decade, to solve the problems of the oil and gas industry, the methods based on artificial intelligence, in particular, on machine learning (ML) methods, have been proposed in the literature. This article provides a review of the literature on the application of ML methods to solve various problems of the oil and gas industry, which allow to determine the potential of ML methods and more widely implement them in the oil and gas industry (pp.52-60).
- Chima C.M., Hills D. Supply-chain management issues in the oil and gas industry // Journal of Business and Economics Research, 2007, vol. 5, no. 6, pp. 27-36.
- Mohammed M., Khan M.B., Bashier E.B.M. Machine learning: algorithms and applications, CRC Press, 2017, 46 p.
- Evgeniou T., Pontil M. Support Vector Machines: Theory and Applications / Machine Learning and Its Applications, Advanced Lectures, 2001, pp. 249-257
- Patterson D.W. Artificial neural networks: Theory and Applications // Prentice Hall, 1996, 477 p.
- Pouyanfar S., Sadiq S., Yan Y., Tian H., Tao Y., Reyes M. P., Shyu M.L, Chen S., Chen S.C., Iyengar S.S. A Survey on Deep Learning: Algorithms, Techniques and Applications // ACM Computing Surveys, 2018, vol. 51, no.5, 36 p.
- Bodenhofer U. Genetic Algorithms: Theory and Applications // Lecture Notes, 2003, 126 p.
- Tsegha E. Assessing the challenges and opportunities in the oil and gas industry // Academic Journal of Interdisciplinary Studies, 2013, vol. 2, no. 12, pp. 129-136.
- Balaji K., Rabiei M., Suicmez V., Hakan C. C., Agharzeyva Z., Tek S., Bulut U., Temizel C. Status of Data-Driven Methods and their Applications in Oil and Gas Industry / SPE Europec featured at 80th EAGE Conference and Exhibition, 2018, 20 p.
- Arehart R. Drill-bit diagnosis with neural networks // SPE Computer Applications, 1990, vol. 2, no. 4, pp. 24-28.
- Bilgesu H., Tetrick, L., Altmis, U., Mohaghegh, S., Ameri, S. A new approach for the prediction of rate of penetration (ROP) values / SPE Eastern Regional Meeting, 1997, pp. 175-180.
- Wang Y., Salehi, S. Application of real-time field data to optimize drilling hydraulics using neural network approach // Journal of Energy Resources Technology, 2015, vol. 137, no. 6, 9 p.
- Ahmadi M.A. Toward reliable model for prediction Drilling Fluid Density at wellbore conditions: a LSSVM model // Neurocomputing, 2016, vol. 211, pp. 143-149
- Yιlmaz S., Demircioglu, C., Akin, S. Application of artiашcial neural networks to optimum bit selection // Computers & Geosciences, 2002, vol. 28, no. 2, pp. 261-269
- Hajizadeh Y. Machine learning in oil and gas; a SWOT analysis approach // Journal of Petroleum Science and Engineering, 2019, vol. 176, pp. 661-663
- Aminu K.T., McGlinchey D. Cowell A. Acoustic signal processing with robust machine learning algorithm for improved monitoring of particulate solid materials in a gas flowline // Flow Measurement and Instrumentation, 2019, vol. 65, pp. 33-44
- Qiao Y., Peng J., Ge L., Wang H. Application of PSO LS-SVM forecasting model in oil and gas production forecast / IEEE 16th International Conference on Cognitive Informatics & Cognitive Computing, 2017, pp. 470-474
- Panja P., Velasco R., Pathak M., Deo M. Application of artificial intelligence to forecast hydrocarbon production from shales // Petroleum 2018, vol.4, no.1, pp.75-89
- Li H., Misra S. Long short-term memory and variational autoencoder with convolutional neural networks for generating nmr t2 distributions / IEEE Geoscience and Remote Sensing Letters, 2018, vol. 16, no. 2, pp. 192-195
- Imamverdiyev Y., Sukhostat L. Lithological facies classification using deep convolutional neural network // Journal of Petroleum Science and Engineering, v.174, March 2019, pp. 216-228
- Abdullayeva F.D., Imamverdiyev Y.N., Development of oil production forecasting method based on Deep Learning // Statistics, Optimization and Information Computing, 2019, vol. 7, pp. 826–839.
- Paltrinieria N., Comfort L., Reniers G. Learning about risk: Machine learning for risk assessment // Safety Science , 2019, vol. 118, pp. 475-486
- Velez-Langs O. Genetic algorithms in oil industry: An overview // Journal of Petroleum Science and Engineering, 2005, vol. 47, no.1-2, pp. 15-22
- Bello O., Teodoriu, C., Yaqoob, T., Oppelt, J., Holzmann, J., Obiwanne, A. Application of artificial intelligence techniques in drilling system design and operations: a state of the art review and future research pathways / SPE Nigeria Annual International Conference and Exhibition, 2016, vol. 5, no. 2, pp. 121-139
- Rahmanifard H., Plaksina, T. Application of artificial intelligence techniques in the petroleum industry: a review // Artificial Intelligence Review, 2019, vol, 52, pp. 2295-2318
- Jin H., Zhang L., Liang W., Ding Q. Integrated leakage detection and localization model for gas pipelines based on the acoustic wave method // Journal of Loss Prevention in the Process Industries, 2014, vol. 27, pp. 74-
- Kristjanpoller W., Minutolo M.C. Forecasting volatility of oil price using an artificial neural network-GARCH model // Expert Systems with Applications, 2016, vol. 65, pp. 233–241.